Efficient sequential correspondence selection by cosegmentation.

IEEE Trans Pattern Anal Mach Intell

Center for Machine Perception, Department ofCybernetics, Faculty of Electrical Engineering, Czech Technical University, Technicka 2, 16627 Praha 6, Czech Republic.

Published: September 2010

In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that 1) has high precision (is highly discriminative), 2) has good recall, and 3) is fast. The sequential decision on the correctness of a correspondence is based on simple statistics of a modified dense stereo matching algorithm. The statistics are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed on the SVM projection computed on progressively larger cosegmented regions. We show experimentally that the proposed sequential correspondence verification (SCV) algorithm significantly outperforms the standard correspondence selection method based on SIFT distance ratios on challenging matching problems.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2009.176DOI Listing

Publication Analysis

Top Keywords

sequential correspondence
8
correspondence selection
8
sequential decision
8
correspondence verification
8
correspondence
5
efficient sequential
4
selection cosegmentation
4
cosegmentation retrieval
4
retrieval object
4
object recognition
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!